Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308573158> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4308573158 abstract "Deep Neural Networks (DNNs) are now widely adopted to solve various problems ranging from speech recognition to image classification. Since DNNs demand a large amount of processing power, their implementation on hardware, i.e., FPGA or ASIC, has received much attention. High-level synthesis is widely used since it significantly boosts productivity and flexibility and requires minimal hardware knowledge. However, when HLS transforms a C implementation to a Register-Transfer Level one, the high parallelism capability of the FPGA is not well-utilized. HLS tools provide a feature called directives through which designers can guide the tool using some defined C pragma statements to improve performance. Nevertheless, finding appropriate directives is another challenge, which needs considerable expertise and experience. This paper proposes DeepFlexiHLS, a two-stage design space exploration flow to find a set of directives to achieve minimal latency. In the first stage, a partition-based method is used to find the directives corresponding to each partition. Aggregating all these directives leads to minimal latency. Experimental results show 54% more speed-up than similar work on VGG neural network. In the second stage, an estimator is implemented to find the latency and resource utilization of various combinations of the found directives. The results form a Pareto-frontier from which the designer can choose if FPGA resources are limited or are not to be entirely used by the DNN module." @default.
- W4308573158 created "2022-11-12" @default.
- W4308573158 creator A5052013615 @default.
- W4308573158 creator A5062612658 @default.
- W4308573158 creator A5063193249 @default.
- W4308573158 creator A5068767700 @default.
- W4308573158 date "2022-10-25" @default.
- W4308573158 modified "2023-09-30" @default.
- W4308573158 title "DeepFlexiHLS: Deep Neural Network Flexible High-Level Synthesis Directive Generator" @default.
- W4308573158 cites W2112796928 @default.
- W4308573158 cites W2276486856 @default.
- W4308573158 cites W2591882361 @default.
- W4308573158 cites W2616014673 @default.
- W4308573158 cites W2727238169 @default.
- W4308573158 cites W2810861508 @default.
- W4308573158 cites W2896983500 @default.
- W4308573158 cites W2950598802 @default.
- W4308573158 cites W2996011401 @default.
- W4308573158 cites W3000394359 @default.
- W4308573158 cites W3014927913 @default.
- W4308573158 cites W3101493857 @default.
- W4308573158 cites W3116598958 @default.
- W4308573158 cites W3211485653 @default.
- W4308573158 cites W3216300721 @default.
- W4308573158 cites W4242577057 @default.
- W4308573158 cites W4294691834 @default.
- W4308573158 doi "https://doi.org/10.1109/norcas57515.2022.9934617" @default.
- W4308573158 hasPublicationYear "2022" @default.
- W4308573158 type Work @default.
- W4308573158 citedByCount "0" @default.
- W4308573158 crossrefType "proceedings-article" @default.
- W4308573158 hasAuthorship W4308573158A5052013615 @default.
- W4308573158 hasAuthorship W4308573158A5062612658 @default.
- W4308573158 hasAuthorship W4308573158A5063193249 @default.
- W4308573158 hasAuthorship W4308573158A5068767700 @default.
- W4308573158 hasConcept C113775141 @default.
- W4308573158 hasConcept C114614502 @default.
- W4308573158 hasConcept C118524514 @default.
- W4308573158 hasConcept C149635348 @default.
- W4308573158 hasConcept C154945302 @default.
- W4308573158 hasConcept C173608175 @default.
- W4308573158 hasConcept C2776221188 @default.
- W4308573158 hasConcept C33923547 @default.
- W4308573158 hasConcept C41008148 @default.
- W4308573158 hasConcept C41112130 @default.
- W4308573158 hasConcept C42812 @default.
- W4308573158 hasConcept C42935608 @default.
- W4308573158 hasConcept C50644808 @default.
- W4308573158 hasConcept C58013763 @default.
- W4308573158 hasConcept C76155785 @default.
- W4308573158 hasConcept C77390884 @default.
- W4308573158 hasConcept C82876162 @default.
- W4308573158 hasConceptScore W4308573158C113775141 @default.
- W4308573158 hasConceptScore W4308573158C114614502 @default.
- W4308573158 hasConceptScore W4308573158C118524514 @default.
- W4308573158 hasConceptScore W4308573158C149635348 @default.
- W4308573158 hasConceptScore W4308573158C154945302 @default.
- W4308573158 hasConceptScore W4308573158C173608175 @default.
- W4308573158 hasConceptScore W4308573158C2776221188 @default.
- W4308573158 hasConceptScore W4308573158C33923547 @default.
- W4308573158 hasConceptScore W4308573158C41008148 @default.
- W4308573158 hasConceptScore W4308573158C41112130 @default.
- W4308573158 hasConceptScore W4308573158C42812 @default.
- W4308573158 hasConceptScore W4308573158C42935608 @default.
- W4308573158 hasConceptScore W4308573158C50644808 @default.
- W4308573158 hasConceptScore W4308573158C58013763 @default.
- W4308573158 hasConceptScore W4308573158C76155785 @default.
- W4308573158 hasConceptScore W4308573158C77390884 @default.
- W4308573158 hasConceptScore W4308573158C82876162 @default.
- W4308573158 hasFunder F4320338080 @default.
- W4308573158 hasLocation W43085731581 @default.
- W4308573158 hasOpenAccess W4308573158 @default.
- W4308573158 hasPrimaryLocation W43085731581 @default.
- W4308573158 hasRelatedWork W1604320855 @default.
- W4308573158 hasRelatedWork W1892041103 @default.
- W4308573158 hasRelatedWork W2134422574 @default.
- W4308573158 hasRelatedWork W2602665985 @default.
- W4308573158 hasRelatedWork W2945560322 @default.
- W4308573158 hasRelatedWork W2997602288 @default.
- W4308573158 hasRelatedWork W3147787617 @default.
- W4308573158 hasRelatedWork W4281757109 @default.
- W4308573158 hasRelatedWork W4323718449 @default.
- W4308573158 hasRelatedWork W4360994686 @default.
- W4308573158 isParatext "false" @default.
- W4308573158 isRetracted "false" @default.
- W4308573158 workType "article" @default.